Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    state of the art

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    it
    0.52
    um
    0.52
    at
    0.51
    </strong>
    0.50
    osynthesis
    0.48
    itting
    0.48
    oculars
    0.47
    using
    0.47
    真的
    0.47
    ıt
    0.46
    POSITIVE LOGITS
     mour
    0.65
     evergreen
    0.56
     fuga
    0.54
     beaded
    0.53
     mourning
    0.50
     pagoda
    0.50
     rom
    0.50
     eternal
    0.50
     ridge
    0.50
     rebirth
    0.49
    Act Density 0.000%

    No Known Activations